We are excited to announce that the groundbreaking IBM MAMMAL (Molecular Aligned Multi-Modal Architecture and Language) model is now accessible for free through our public API at Cure Cancer With AI. Developed by IBM Research, MAMMAL is a state-of-the-art multi-modal biomedical foundation model designed to enhance cancer and drug discovery research. But what exactly does this mean, and how can it benefit researchers and innovators in the field?

What is IBM MAMMAL?

MAMMAL is a sophisticated multi-modal model that integrates information across various biological domains, including proteins, small molecules, and gene/omics data. By aligning these different modalities, MAMMAL provides a comprehensive framework that enables researchers to analyze biological interactions and predict outcomes more effectively. This capability is particularly vital in the context of drug discovery and cancer research, where understanding the relationships between proteins and small molecules is crucial for developing effective therapies.

The name “Molecular Aligned Multi-Modal Architecture and Language” reflects its innovative approach to representing biological data in a unified manner. This means that MAMMAL can handle complex tasks such as classification, regression, and generation—all of which are essential in biomedical research.

The Research Behind MAMMAL

The power of MAMMAL is backed by rigorous research, as detailed in the npj Drug Discovery (Nature) paper. Trained on approximately 2 billion biological samples, MAMMAL has been evaluated across 11 diverse drug discovery tasks. Remarkably, it achieved new state-of-the-art results on 9 of these tasks, demonstrating its exceptional predictive capabilities and versatility.

This extensive training allows MAMMAL to leverage vast amounts of biological data, making it an invaluable tool for researchers aiming to uncover new insights in drug discovery and cancer treatment. Its ability to integrate multiple data types means that it can provide more informed predictions than models that focus on only one type of data.

MAMMAL in the Cure Cancer With AI API

Now, let's explore how researchers and developers can utilize the MAMMAL model through our free public API. We currently offer three key endpoints that provide essential predictions:

• Protein-Protein Interaction (PPI):

  Endpoint: /api/v1/mammal/ppi

  This endpoint predicts whether two proteins will interact. By providing two amino-acid sequences (protein_a and protein_b), users will receive a binding-affinity class label of "1" (indicating interaction) or "0" (indicating no interaction).

• Drug-Target Interaction (DTI):

  Endpoint: /api/v1/mammal/dti

  This endpoint predicts the interaction between a drug and a target protein. Users need to input a target protein's amino-acid sequence (target_seq) along with a drug represented in SMILES notation (drug_seq). The output will provide a predicted pKd value, where a higher number indicates a stronger predicted binding affinity.

• ClinTox Clinical-Trial Toxicity:

  Endpoint: /api/v1/mammal/clintox

  This endpoint predicts the toxicity of a compound in clinical trials. Users must input the compound in SMILES notation (smiles), and the model returns a toxicity prediction, with a score of "1" indicating toxicity or likely failure in trials, and "0" indicating non-toxicity.

Each of these endpoints operates via POST requests and returns results in JSON format. Though the model is CPU-bound and may take up to 60 seconds to respond, the insights provided can significantly expedite research processes and foster innovation in drug discovery.

Start Using It for Free

We invite you to take advantage of this powerful tool! To get started, you can create a free API key at /api-keys. The free tier allows for up to 100 requests per hour per key, making it accessible for individual researchers, small teams, and anyone interested in exploring the capabilities of MAMMAL.

For comprehensive documentation, including parameters and code samples, please visit /developers. Our API documentation will guide you through using the endpoints effectively, ensuring you can harness the full potential of MAMMAL in your research.

Conclusion

In summary, the MAMMAL AI model is now freely available through Cure Cancer With AI, providing researchers with invaluable predictive capabilities in protein–protein interactions, drug–target interactions, and clinical trial toxicity. We encourage you to explore these tools and integrate them into your research workflows.

However, it's important to remember that the predictions generated by MAMMAL are research signals and should not be considered medical or clinical advice. Always consult a qualified healthcare professional for any medical concerns.

Start unlocking the potential of MAMMAL today on curecancerwithai.com!

To dive deeper into practical AI-for-cancer-research updates, explore our latest blog posts, learn more about our mission, and see how you can support ongoing work on our donations page.

Cure Cancer With AI is an educational research and information platform. It does not provide medical advice, diagnosis, or treatment recommendations; always discuss care decisions with a qualified healthcare professional.